Abstract
Counterattacks in soccer are an important strategical component for goal scoring. Previous work in the literature has described their impact and has formulated descriptive advice on successful actions during a counterattack. In contrast, in this work, we propose the notion of expected counter, i.e., quantifying forward progress by the ball-winning team at the moment of the turnover. Therefore, we apply a previously proposed framework for understanding complex sequences in soccer. Using this framework, we perform a novel feature-specific assessment that yields (a) critical feature values, (b) relevant feature pitch zones, and (c) feature prediction capabilities. The insights from this assessment step allow for creating concrete guidelines for optimal behavior in and out of possession. Thus, we find that preparing horizontally spaced pass options facilitates an own counterattack in case of a ball win while moving as a compact unit prevents an opposing counterattack in case of a ball loss. As a final step, we generalize our results by creating a predictive XGBoost model that outperforms a location-based baseline but still shows room for improvement.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balague, N., Torrents, C., Hristovski, R., Davids, K., Araújo, D.: Overview of complex systems in sport. J. Syst. Sci. Complex. 26(1), 4–13 (2013). https://doi.org/10.1007/s11424-013-2285-0
Bauer, P., Anzer, G.: Data-driven detection of counterpressing in professional football: a supervised machine learning task based on synchronized positional and event data with expert-based feature extraction. Data Min. Knowl. Disc. 35(5), 2009–2049 (2021). https://doi.org/10.1007/s10618-021-00763-7
Bauer, P., Anzer, G.: A goal scoring probability model for shots based on synchronized positional and event data in football (soccer). Front. Sports Active Living 3, 53 (2021). https://doi.org/10.3389/fspor.2021.624475
Biermann, H., Theiner, J., Bassek, M., Raabe, D., Memmert, D., Ewerth, R.: A unified taxonomy and multimodal dataset for events in invasion games. In: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports, pp. 1–10. ACM, Virtual Event China (2021). https://doi.org/10.1145/3475722.3482792
Biermann, H., Wieland, F.G., Timmer, J., Memmert, D., Phatak, A.: Towards expected counter - using comprehensible features to predict counterattacks. In: Brefeld, U., Davis, J., Van Haaren, J., Zimmermann, A. (eds.) MLSA 2022. CCIS, vol. 1783, pp. 3–13. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-27527-2_1
Delaunay, B., et al.: Sur la sphere vide. Izv. Akad. Nauk SSSR, Otdelenie Matematicheskii i Estestvennyka Nauk 7(793–800), 1–2 (1934)
Fernández, J., Bornn, L., Cervone, D.: A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions. Mach. Learn. 110(6), 1389–1427 (2021). https://doi.org/10.1007/s10994-021-05989-6
Frencken, W., Lemmink, K., Delleman, N., Visscher, C.: Oscillations of centroid position and surface area of soccer teams in small-sided games. Eur. J. Sport Sci. 11(4), 215–223 (2011). https://doi.org/10.1080/17461391.2010.499967
Hockeyviz: Smoothing: How to (2023)
Lago-Ballesteros, J., Lago-Peñas, C., Rey, E.: The effect of playing tactics and situational variables on achieving score-box possessions in a professional soccer team. J. Sports Sci. 30(14), 1455–1461 (2012)
Lepschy, H., Wäsche, H., Woll, A.: Success factors in football: an analysis of the German Bundesliga. Int. J. Perform. Anal. Sport 20(2), 150–164 (2020). https://doi.org/10.1080/24748668.2020.1726157
Liu, G., Luo, Y., Schulte, O., Kharrat, T.: Deep soccer analytics: learning an action-value function for evaluating soccer players. Data Min. Knowl. Disc. 34(5), 1531–1559 (2020)
LLC, S: Playing Styles Definition by StatsPerform (2023)
Merhej, C., Beal, R.J., Matthews, T., Ramchurn, S.: What happened next? Using deep learning to value defensive actions in football event-data. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 3394–3403. ACM, Virtual Event Singapore (2021). https://doi.org/10.1145/3447548.3467090
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Raudonius, L., Allmendinger, R.: Evaluating football player actions during counterattacks. In: Yin, H., et al. (eds.) IDEAL 2021. LNCS, vol. 13113, pp. 367–377. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-91608-4_36
Robberechts, P., Davis, J.: How data availability affects the ability to learn good xG models. In: Brefeld, U., Davis, J., Van Haaren, J., Zimmermann, A. (eds.) MLSA 2020. CCIS, vol. 1324, pp. 17–27. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64912-8_2
Sahasrabudhe, A., Bekkers, J.: A graph neural network deep-dive into successful counterattacks. In: MIT Sloan Sports Analytics Conference, vol. 17 (2023)
Tenga, A., Kanstad, D., Ronglan, L.T., Bahr, R.: Developing a new method for team match performance analysis in professional soccer and testing its reliability. Int. J. Perform. Anal. Sport 9(1), 8–25 (2009). https://doi.org/10.1080/24748668.2009.11868461
Van Haaren, J.: “Why would I trust your numbers?” On the explainability of expected values in soccer. arXiv preprint arXiv:2105.13778 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Appendix
A Appendix
For the predictive XGBoost models, a range of different hyperparameters were examined. Therefore, training was done on the training set (70% of turnovers) and the performance of different hyperparameter configurations was compared on the test set (30% of turnovers). Due to the fact, that the focus of work does not lie on generating an automatic model, we avoid using a more sophisticated approach, e.g., using cross-validation or a separate validation set. A list of the evaluated hyperparameters is provided in Table 6. Admittedly, our search space is limited, yet we plan to expand it in future. An explanation of the different hyperparameter configurations of the best XGBoost models, encrypted as superscripts in Table 3, is given in Table 7.
Detailed lists of the best ranked features for both teams are presented in Tables 8 and 9.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Biermann, H., Yang, W., Wieland, FG., Timmer, J., Memmert, D. (2024). Quantification of Turnover Danger with xCounter. In: Brefeld, U., Davis, J., Van Haaren, J., Zimmermann, A. (eds) Machine Learning and Data Mining for Sports Analytics. MLSA 2023. Communications in Computer and Information Science, vol 2035. Springer, Cham. https://doi.org/10.1007/978-3-031-53833-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-53833-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53832-2
Online ISBN: 978-3-031-53833-9
eBook Packages: Computer ScienceComputer Science (R0)